fix(improvement): analyze baseline traces before generation 0 so single-generation runs propose with trace context#334
Merged
Conversation
…le-generation runs propose with trace context
drewstone
added a commit
that referenced
this pull request
Jul 9, 2026
* fix(campaign): export composite proposer * chore(release): lock python client to 0.110.1 * fix(improvement): analyze baseline traces before generation 0 so single-generation runs propose with trace context (#334) * fix(campaign): export composite proposer * chore(release): lock python client to 0.110.1 * fix(campaign): align composite proposer docs and release checks * docs(campaign): distinguish proposer composition modes * style(release): align version check formatting
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The gap
analyzeGenerationonly fired between generations, so a run withgenerations=1proposed blind: baseline traces existed, but no analysis of them ever reached the proposer.The fix
One
analyzeGenerationcall immediately after the baseline eval, recorded under agen -1convention so it is distinct from between-generation analyses. Guarded no-op when there is no producer or no baseline traces, so nothing changes for configurations that cannot use it.Tests
43/43 passing across the two touched suites (
tests/campaign/presets.test.ts,tests/contract-self-improve.test.ts), including three new tests covering the baseline analysis call, the gen -1 convention, and the guarded no-op.🤖 Generated with Claude Code